Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ologically
    -0.06
    vature
    -0.06
    _SANITIZE
    -0.06
    .Non
    -0.06
     chronological
    -0.06
    >Email
    -0.06
    roph
    -0.06
    shell
    -0.06
    委員
    -0.06
    brick
    -0.06
    POSITIVE LOGITS
    ắc
    0.07
    _configs
    0.07
    aeda
    0.06
    .Version
    0.06
     �
    0.06
    199
    0.06
     cada
    0.06
    ่สามารถ
    0.06
     tog
    0.06
     hoạch
    0.06
    Act Density 0.022%

    No Known Activations